Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    if so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кок
    0.44
     leftWheel
    0.38
     freck
    0.37
    >//
    0.36
    嬠
    0.36
    Antaeotricha
    0.35
     carboxylic
    0.34
     현대
    0.34
     தன்ன
    0.34
     自
    0.33
    POSITIVE LOGITS
     тогда
    0.71
     then
    0.70
     allora
    0.70
     Тогда
    0.70
     alors
    0.68
     entonces
    0.65
     would
    0.63
     তাহলে
    0.63
     akkor
    0.63
     wówczas
    0.63
    Act Density 0.122%

    No Known Activations